A global reference data set for land cover mapping at 10 m resolution

Abstract. This paper presents a unique global reference data set for land cover mapping at a 10 m resolution, aligned with Sentinel-2 imagery for the year 2015. It contains more than 16.5 million data records at a 10 m resolution (or 165 K data records at 100 m) and information on 12 different land cover classes. The data set was collected by a group of experts through visual interpretation of very high resolution imagery (e.g., from Google Maps, Microsoft Bing, ESRI World), along with other sources of information provided in the Geo-Wiki platform (e.g., Normalized Difference Vegetation Index time series, Sentinel-2 image time series, geo-tagged photographs, and street view imagery). To ensure high quality and consistency among the experts that collected the data, regular coordination meetings took place, there were regular quality checks of expert submissions, and comparison with regional land cover maps was undertaken. This extensive reference land cover data set can be used in various applications, e.g., land cover analysis, including mapping and quality verification, ecosystems mapping and modelling, and biodiversity and cropland studies, among others. The data set is available for download at https://zenodo.org/records/14871660.

Authors

Institutions

Publication Details

Published
2025-08-21
DOI
https://doi.org/10.5194/essd-2025-468
Primary Topic
Remote Sensing and Land Use
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

A global reference data set for land cover mapping at 10 m resolution

Michael Cherlet, Bruno Smets, Ivelina Georgieva, Ian McCallum et al.
Remote Sensing and Land Use
article

A global reference data set for land cover mapping at 10 m resolution

Michael Cherlet, Bruno Smets, Ivelina Georgieva, Ian McCallum, Ruben Van De Kerchove, Nandin‐Erdene Tsendbazar, Steffen Fritz, Marcel Buchhorn, Martin Herold, Dmitry Schepaschenko, Myroslava Lesiv, Daniele Zanaga, Martina Duerauer, Linda See, Luc Bertels
article en

Abstract

Abstract. This paper presents a unique global reference data set for land cover mapping at a 10 m resolution, aligned with Sentinel-2 imagery for the year 2015. It contains more than 16.5 million data records at a 10 m resolution (or 165 K data records at 100 m) and information on 12 different land cover classes. The data set was collected by a group of experts through visual interpretation of very high resolution imagery (e.g., from Google Maps, Microsoft Bing, ESRI World), along with other sources of information provided in the Geo-Wiki platform (e.g., Normalized Difference Vegetation Index time series, Sentinel-2 image time series, geo-tagged photographs, and street view imagery). To ensure high quality and consistency among the experts that collected the data, regular coordination meetings took place, there were regular quality checks of expert submissions, and comparison with regional land cover maps was undertaken. This extensive reference land cover data set can be used in various applications, e.g., land cover analysis, including mapping and quality verification, ecosystems mapping and modelling, and biodiversity and cropland studies, among others. The data set is available for download at https://zenodo.org/records/14871660.

International Institute for Applied Systems Analysis (AT), European Commission (BE), GFZ Helmholtz Centre for Geosciences (DE), Wageningen University & Research (NL)
Joint Research Centre
Openalex Percentile: Top 73%
Remote Sensing and Land Use
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.